Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Xm
    -0.06
     Ts
    -0.06
    	box
    -0.06
    И
    -0.06
    Box
    -0.06
    (join
    -0.06
     cents
    -0.06
    י�
    -0.06
     hoof
    -0.06
     soil
    -0.06
    POSITIVE LOGITS
    监听页面
    0.07
    />.
    0.07
    ://"
    0.06
    英国
    0.06
    海外
    0.06
    طب
    0.06
    รอบ
    0.06
     intoler
    0.06
    _MAIL
    0.06
    _Construct
    0.06
    Act Density 0.024%

    No Known Activations